home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!destroyer!ubc-cs!unixg.ubc.ca!kakwa.ucs.ualberta.ca!alberta!arms
- From: arms@cs.UAlberta.CA (Bill Armstrong)
- Subject: Re: Neural Nets and Brains
- Message-ID: <arms.712027061@spedden>
- Sender: news@cs.UAlberta.CA (News Administrator)
- Nntp-Posting-Host: spedden.cs.ualberta.ca
- Organization: University of Alberta, Edmonton, Canada
- References: <arms.711986585@spedden> <1992Jul24.164544.11876@cs.ucf.edu>
- Date: Sat, 25 Jul 1992 01:17:41 GMT
- Lines: 38
-
- clarke@acme.ucf.edu (Thomas Clarke) writes:
-
- >In article <arms.711986585@spedden> arms@cs.UAlberta.CA (Bill Armstrong)
- >writes:
- >> .... My point
- >> was that BP nets use continuous signals and the brain doesn't -- an
- >> obvious very significant difference. I was asking why people would
- >> expect to understand the brain by studying a system (BP) that is
- >> *different* at the most basic level of signalling.
- >>
- >> Don't you agree that if the brain works on 0-1 signals, then to study
- >> the brain one could beneficially look at logical systems?
-
- >I believe the brain may well use continuous or analog signals.
-
- >While individual neuron action potentials are on or off, they
- >often occcur in trains of varying frequency. The time-density of
- >action potentials then forms an analog or continuous variable
- >that may be processed in much the same way as a BP network.
-
- >In fact, if you posit a central clock in the brain, the phase of
- >the action potentials with respect to the clock provide another
- >possibility for a continuous variable. Indeed, both phase and
- >density could work together to make the brain a
- >complex-valued neural network :-)
-
- Thank you. A nice explanation. Unfortunately, taking phase and
- density of pulses into account makes for quite a complex, non-linear
- system (refractory periods, neurotransmitter release and uptake,...).
- If the brain works that way, then the simple multiply-add
- accumulations of backprop are over-simplified, aren't they? Then
- maybe both backprop and ALNs are useless for the purposes of brain
- modelling.
- --
- ***************************************************
- Prof. William W. Armstrong, Computing Science Dept.
- University of Alberta; Edmonton, Alberta, Canada T6G 2H1
- arms@cs.ualberta.ca Tel(403)492 2374 FAX 492 1071
-